submit.py

from pathlib import Path
import tempfile
from typing import BinaryIO
import json

import gradio as gr
from datetime import datetime
import uuid

from constants import API, SUBMISSIONS_REPO
from validation import validate_csv_file


def make_submission(
    submitted_file: BinaryIO,
    user_state,
    anonymous_state,
    submission_type: str = "GDPa1",
):
    if user_state is None:
        raise gr.Error("You must submit your username to submit a file.")

    if submitted_file is None:
        raise gr.Error("Please upload a CSV file before submitting.")

    file_path = submitted_file.name

    if not file_path:
        raise gr.Error("Uploaded file object does not have a valid file path.")

    path_obj = Path(file_path)

    if path_obj.suffix.lower() != ".csv":
        raise gr.Error("File must be a CSV file. Please upload a .csv file.")

    timestamp = datetime.utcnow().isoformat()
    submission_id = str(uuid.uuid4())

    with path_obj.open("rb") as f_in:
        file_content = f_in.read().decode("utf-8")

        validate_csv_file(file_content, submission_type)

        # write to dataset
        filename = f"{submission_id}.json"
        # Note: This may be represented as Parquet in the future, so the schema needs to stay consistent
        record = {
            "submission_id": submission_id,
            "submission_filename": filename,
            "submission_time": timestamp,
            "evaluated": False,
            "user": user_state,
            "anonymous": anonymous_state,
            "csv_content": file_content,
        }
        with tempfile.NamedTemporaryFile(mode="w", suffix=".json", delete=False) as tmp:
            json.dump(record, tmp, indent=2)
            tmp.flush()
            tmp_name = tmp.name

        API.upload_file(
            path_or_fileobj=tmp_name,
            path_in_repo=filename,
            repo_id=SUBMISSIONS_REPO,
            repo_type="dataset",
            commit_message=f"Add submission for {user_state} at {timestamp}",
        )
        Path(tmp_name).unlink()

    return "✅ Your submission has been received! Sit tight and your scores will appear on the leaderboard shortly."